What is mcp-web-docs CLAUDE.md?

Project instructions for an AI coding agent working on a TypeScript server that crawls, indexes, and searches website documentation. They describe the project, tools, coding rules, and tests.

Use them when changing the MCP Web Docs project, especially when writing TypeScript, adding tests with Vitest, or working with its web crawler and documentation search.

They give the agent the project context and local rules needed to make consistent changes. This reduces guesswork about code style, imports, testing, and the server's storage and search systems.

mcp-web-docs CLAUDE.md — Instructions file by cosmocoder

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/cosmocoder/mcp-web-docs/claude-md

Clone the repo

git clone --depth 1 https://github.com/cosmocoder/mcp-web-docs

Per session 839 This file is loaded in full into every session.

When invoked 839 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00839	$0.00839
Opus 5	$0.00419	$0.00419
Sonnet 5	$0.00168	$0.00168
Haiku 4.5	$0.00084	$0.00084

Measured 2d ago against content hash 2b60e864716b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-web-docs CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code Guidelines for MCP Web Docs

This is a TypeScript MCP (Model Context Protocol) server project for crawling and indexing web documentation.

Quick Reference

For comprehensive guidelines, see AGENTS.md in the project root.

Project Overview

MCP Web Docs is a self-hosted MCP server that crawls, indexes, and searches documentation from any website. It provides:

Universal web crawling with Playwright/Crawlee
Hybrid search (full-text + semantic/vector)
Authentication support for protected documentation
Local embeddings with FastEmbed (no API keys needed)

Tech Stack

Runtime: Node.js >= 24, npm >= 11
Language: TypeScript (ES2022, NodeNext modules)
Testing: Vitest
Storage: SQLite (metadata) + LanceDB (vectors)

Essential Rules

Code Style

TypeScript with strict mode
Always use .js extensions in imports (ESM requirement)
Follow existing patterns in the codebase

Testing

Tests are co-located: *.test.ts next to source files
Use Vitest globals: describe, it, expect, vi
Mock embeddings: createMockEmbeddings() from src/__mocks__/embeddings.ts
Use vi.hoisted() for mocks configured before imports

Critical Constraints

Never log to stdout - MCP servers use stdio for JSON-RPC
Use logger from src/util/logger.ts (writes to stderr)
Validate inputs with Zod schemas from src/util/security.ts
Use validatePublicUrl() for SSRF protection

Key Commands

npm test              # Run tests
npm run build         # Build TypeScript
npm run lint          # Run ESLint
npm run prettier      # Format code
npm run test:coverage # Test with coverage
npm run test:types    # Type check

Architecture

src/
├── index.ts          # CLI bootstrap and signal handling
├── server.ts         # MCP server and tool handlers
├── crawler/          # Web crawling (Playwright/Crawlee)
├── processor/        # Content processing
├── storage/          # SQLite + LanceDB
├── embeddings/       # FastEmbed vectors
├── indexing/         # Workflow, status tracking, queue management
└── util/             # Logger, security, helpers

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 100 lines · 839 tokens per session scan A 2b60e864716b

Subscribe to this mod's changes

mcp-web-docs CLAUDE.md is an instructions file published in the GitHub repository cosmocoder/mcp-web-docs (1 stars, last pushed 8d ago), licensed MIT. It adds 839 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-web-docs CLAUDE.md